© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81573
    Prev
    Next
    INDEX
    Explanations

    murder and associated crimes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Requ
    -0.90
     frauds
    -0.84
     scares
    -0.82
     éxitos
    -0.82
    ांक
    -0.81
     Adjustments
    -0.80
    つも
    -0.80
    taciones
    -0.79
    auré
    -0.79
    を得
    -0.78
    POSITIVE LOGITS
    ously
    1.27
    ous
    1.22
     spree
    1.16
     mystery
    1.11
     Murder
    1.05
     weapon
    1.04
     Mystery
    1.04
    Murder
    1.02
    mystery
    1.02
     committed
    0.99
    Activations Density 0.011%

    No Known Activations